FoodPuzzle: Developing Large Language Model Agents as Flavor Scientists

• URL: http://arxiv.org/abs/2409.12832v3
• Date: Mon, 7 Oct 2024 01:26:23 GMT
• Title: FoodPuzzle: Developing Large Language Model Agents as Flavor Scientists
• Authors: Tenghao Huang, Donghee Lee, John Sweeney, Jiatong Shi, Emily Steliotes, Matthew Lange, Jonathan May, Muhao Chen,
• Abstract summary: We present a new problem domain for scientific agents in flavor science, conceptualized as the generation of hypotheses for flavor profile sourcing and understanding. We propose a novel Scientific Agent approach, integrating in-context learning and retrieval augmented techniques to generate grounded hypotheses. Experimental results indicate that our model significantly surpasses traditional methods in flavor profile prediction tasks.
• Score: 51.97629078968826
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Flavor development in the food industry is increasingly challenged by the need for rapid innovation and precise flavor profile creation. Traditional flavor research methods typically rely on iterative, subjective testing, which lacks the efficiency and scalability required for modern demands. This paper presents three contributions to address the challenges. Firstly, we define a new problem domain for scientific agents in flavor science, conceptualized as the generation of hypotheses for flavor profile sourcing and understanding. To facilitate research in this area, we introduce the FoodPuzzle, a challenging benchmark consisting of 978 food items and 1,766 flavor molecules profiles. We propose a novel Scientific Agent approach, integrating in-context learning and retrieval augmented techniques to generate grounded hypotheses in the domain of food science. Experimental results indicate that our model significantly surpasses traditional methods in flavor profile prediction tasks, demonstrating its potential to transform flavor development practices.

Related papers

• A topological analysis of the space of recipes [0.0]
  We introduce the use of topological data analysis, especially persistent homology, in order to study the space of culinary recipes. In particular, persistent homology analysis provides a set of recipes surrounding the multiscale "holes" in the space of existing recipes.
  arXiv  Detail & Related papers  (2024-06-12T01:28:16Z)
• Understanding the Limitations of Diffusion Concept Algebra Through Food [68.48103545146127]
  latent diffusion models offer crucial insights into biases and concept relationships. The food domain offers unique challenges through complex compositions and regional biases. We reveal measurable insights into the model's ability to capture and represent the nuances of culinary diversity.
  arXiv  Detail & Related papers  (2024-06-05T18:57:02Z)
• LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery [141.39722070734737]
  We propose to enhance the knowledge-driven, abstract reasoning abilities of Large Language Models with the computational strength of simulations. We introduce Scientific Generative Agent (SGA), a bilevel optimization framework. We conduct experiments to demonstrate our framework's efficacy in law discovery and molecular design.
  arXiv  Detail & Related papers  (2024-05-16T03:04:10Z)
• NutritionVerse-Direct: Exploring Deep Neural Networks for Multitask Nutrition Prediction from Food Images [63.314702537010355]
  Self-reporting methods are often inaccurate and suffer from substantial bias. Recent work has explored using computer vision prediction systems to predict nutritional information from food images. This paper aims to enhance the efficacy of dietary intake estimation by leveraging various neural network architectures.
  arXiv  Detail & Related papers  (2024-05-13T14:56:55Z)
• Extracting chemical food safety hazards from the scientific literature automatically using large language models [0.0]
  It is unfeasible for food safety experts to read all relevant literature related to food safety and the occurrence of hazards in the food chain. It is important that food safety experts are aware of the newest findings and can access this information in an easy and concise way. In this study, an approach is presented to automate the extraction of chemical hazards from the scientific literature through large language models.
  arXiv  Detail & Related papers  (2024-05-01T08:02:10Z)
• ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models [56.08917291606421]
  ResearchAgent is a large language model-powered research idea writing agent. It generates problems, methods, and experiment designs while iteratively refining them based on scientific literature. We experimentally validate our ResearchAgent on scientific publications across multiple disciplines.
  arXiv  Detail & Related papers  (2024-04-11T13:36:29Z)
• FIRE: Food Image to REcipe generation [10.45344523054623]
  Food computing aims to develop end-to-end intelligent systems capable of autonomously producing recipe information for a food image. This paper proposes FIRE, a novel methodology tailored to recipe generation in the food computing domain. We showcase two practical applications that can benefit from integrating FIRE with large language model prompting.
  arXiv  Detail & Related papers  (2023-08-28T08:14:20Z)
• Cook-Gen: Robust Generative Modeling of Cooking Actions from Recipes [6.666528076345153]
  Food computation models have become increasingly popular in assisting people in maintaining healthy eating habits. In this study, we explore the use of generative AI methods to extend current food computation models to include cooking actions. We propose novel aggregation-based generative AI methods, Cook-Gen, that reliably generate cooking actions from recipes.
  arXiv  Detail & Related papers  (2023-06-01T18:49:47Z)
• SciMON: Scientific Inspiration Machines Optimized for Novelty [68.46036589035539]
  We explore and enhance the ability of neural language models to generate novel scientific directions grounded in literature. We take a dramatic departure with a novel setting in which models use as input background contexts. We present SciMON, a modeling framework that uses retrieval of "inspirations" from past scientific papers.
  arXiv  Detail & Related papers  (2023-05-23T17:12:08Z)
• A new Reinforcement Learning framework to discover natural flavor molecules [0.0]
  This work proposes a novel framework based on Scientific Machine Learning to undertake an emerging problem in flavor engineering and industry. The molecules are evaluated regarding the synthetic accessibility, the number of atoms, and the likeness to a natural or pseudo-natural product.
  arXiv  Detail & Related papers  (2022-09-13T10:12:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.